School of Engineering and Applied Sciences
School of Arts and Sciences
University of Pennsylvania
I am a postdoc at the University of Pennsylvania. I got my PhD in Engineering from the University of Cambridge and my BSc/Diploma in Computer Engineering from the University of Chile. My background is mainly in Physics, Mathematics and Computer Science.
I am moving to London.
I am interested in cybernetics and in the mathematical foundations of intelligent behaviour. I study the links between various topics such as Bayesian probability theory, information theory, stochastic control, theoretical economics, causality, statistical mechanics, ergodic theory and complexity theory. Other areas of interest are computational neuroscience, psychology and epistemology. Also, I'm a huge fan of minimalistic algorithms.
Most of my work centers on information-theoretic and statistical mechanical approaches to learning and control, leading to contributions in bounded rationality models and recasting adaptive control as a causal inference problem. I have also worked on causal induction, and on game- and decision-theoretic models in computational neuroscience.
To get a sense of my work, please refer to:
I was part of the former Tuebingen group on Sensorimotor Learning and Decision Making, where some of the now widespread ideas on Thompson sampling, causality, and thermodynamic methods for reinforcement learning have originated. Check out its members' sites:
|A Synthesis of automated planning and reinforcement learning for efficient, robust decision-making https://t.co/uBcf6mefQ0 |
About 8 hours, 6 mins ago by: Pedro A. Ortega (@AdaptiveAgents)
|Regularized Policy Iteration with Nonparametric Function Spaces https://t.co/FsgfjkZy43 |
About 14 hours, 7 mins ago by: Pedro A. Ortega (@AdaptiveAgents)
|Information Foraging and Change Detection for Automated Science Exploration https://t.co/pmd76irZBI |
About 3 days, 8 hours ago by: Pedro A. Ortega (@AdaptiveAgents)
|Towards Deep Compositional Networks https://t.co/IIAUW9OGHr |
About 3 days, 14 hours ago by: Pedro A. Ortega (@AdaptiveAgents)
|An Intelligent Lighting System: Learn User Preferences from Inconsistent Feedback https://t.co/ashjNrohJs |
About 4 days, 8 hours ago by: Pedro A. Ortega (@AdaptiveAgents)